Searcharxiv⌕ Search

arXiv subjects

Shanghang Zhang

Publications and source records attributed to Shanghang Zhang.

At least 19 recordsLinked to original sources

Data Pyramid for Embodied Manipulation: A Survey

Multimodal foundation models learned to see and to speak by consuming the whole internet. Embodied agents admit no such shortcut, since they require data that couple observations with physical states and actions. These signals can be provided, to varying degrees, by multiple data sources. In this work, we organize the embodied data ecosystem as a "pyramid'' spanning five complementary sources: real-robot data, UMI-style data, egocentric and exocentric data, simulation data, and general vision-language data. We organize the pyramid around the tension between scalability and robot alignment, and further characterize each source in terms of data quality, diversity, reusability, and physical fidelity. We then analyze recent embodied foundation models through the lens of data recipes, examining how different sources are selected, aligned, and mixed during pretraining. For embodied brain models, vision-language-action models, and world-action models alike, we relate data composition to capabilities in perception, reasoning, planning, action generation, and world prediction. To facilitate community use, we additionally consolidate over 10,000 hours of trajectories from widely used robot datasets into a unified LeRobot format, with transparent frame-level quality annotations for filtering. We close by discussing six open challenges: building large-scale tactile datasets, collecting failure and recovery data, developing scalable data-collection pipelines, aligning actions across embodiments, leveraging egocentric data for dexterous manipulation, and designing principled data recipes for robot learning. We hope this work lays the foundation for the design of next-generation embodied systems.

cs.RO↗

Ego Guidance: Enhancing Robot Policy Learning with Action-Free Human Egocentric Videos

In this paper, we investigate how human egocentric videos can benefit robot policy learning without action supervision. Building on a pretrained VLM, we propose Shared Prediction on Action and Representation (SPAR), an MoT architecture in which future visual state prediction can provide independent and complementary learning signals alongside action prediction. We find that representations learned from egocentric videos improve downstream performance on out-of-distribution robot tasks, with further gains as video data scales. We also study the effects of objective choices and data curation, providing insights into how to leverage action-free videos for scalable robot learning.

cs.RO↗

LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning

World Action Models (WAMs) have recently emerged as a promising paradigm for robotic manipulation, endowing policies with strong capabilities for modeling temporal and physical dynamics. Existing WAMs, encompassing both video-first action prediction and joint video-action modeling, directly transfer global physical representations from world models to action generation. However, global scene representations may underemphasize local robot-object interactions, creating a mismatch between representations optimized for world evolution and those required for manipulation. To bridge this gap, we propose LaST0.5, a novel WAM that introduces an interaction-centric physical representation between world modeling and action generation. Specifically, LaST0.5 learns a compact interaction-centric latent space under the supervision of visual interaction cues between the robot and the environment. This reasoning space is instantiated as a latent expert that bridges the world expert and the action expert within a Mixture-of-Transformers architecture. Furthermore, LaST0.5 performs adaptive world-to-action transfer by jointly predicting future representations and progress values, using progress consistency to adjust action execution and trigger future resampling. Finally, we pretrain LaST0.5 on a large-scale robotic data corpus comprising over 14k hours of data, establishing interaction-centric physical reasoning as a scalable and effective paradigm. LaST0.5 achieves 99.5% on LIBERO, surpasses the previous state of the art on ten evaluated RLBench tasks, and demonstrates robust long-horizon execution and precise dexterous manipulation in real-world experiments.

cs.RO↗

WorldBridge: Bridging Video and Action for Task Generalization in World Action Models

Achieving the broad task generalization of embodied models in physical environments remains a central challenge in robot learning. We study this challenge in World Action Models (WAMs) through two complementary capabilities: video generalization, which predicts the visual evolution of new tasks, and action generalization, which translates these predictions into executable behavior through a video-to-action bridge. By varying video and action supervision for tasks outside an initial training set, we examine their respective contributions to task transfer. On RoboTwin 2.0, using only in-distribution video-action supervision yields a 25.07% success rate on out-of-distribution tasks. Introducing videos of these tasks without their action labels raises success to 55.90%, while adding just one action-labeled demonstration per task further improves it to 70.70%. These findings suggest that broader video coverage enables task transfer by leveraging existing inverse-dynamics capabilities, while even sparse action supervision further strengthens those capabilities. Guided by this perspective, we introduce WorldBridge, a WAM with separate video and action experts connected through structured attention and trained with joint flow matching. WorldBridge incorporates visual memory at two temporal scales and action forcing, alongside a unified data processing pipeline that standardizes and filters heterogeneous robot trajectories and egocentric hand-derived supervision. Across multiple manipulation benchmarks, WorldBridge achieves state-of-the-art performance among the compared methods, including 96.23% on RoboTwin 2.0 full data setting and 80.9% on clean to random setting, 82.8% on RoboCasa GR1 TableTop, and 57.6% on DOMINO Level-1. Our study highlights the complementary roles of video prediction and action grounding in developing robots that generalize across tasks.

cs.RO↗

CANDO: Conservative Action-Noise Directional Optimization for Residual Reinforcement Learning

Pretrained generative policies provide strong behavior priors for robot control, but adapting them efficiently with online reinforcement learning remains difficult. A central challenge is how to improve a frozen generative policy without destroying the structure learned from offline demonstrations. Noise-space residual methods address this by modifying the policy's input noise, but existing noise-space methods typically regulate adaptation through fixed latent feasible regions, which may exclude valuable noise edits. In contrast, action-space residual methods are more sample-efficient, but their efficiency can still be further improved. We propose Conservative Noise Directional Optimization (CNDO), a noise-space residual RL method that improves a frozen generative policy by learning state- and noise-conditioned directions around Gaussian latent samples. CNDO removes predefined latent feasible regions and instead regulates noise-space adaptation through the soft conservative constraint, which consists of conservative value estimation and gated execution. We further introduce Conservative Action-Noise Directional Optimization (CANDO), which adds an action-space residual, combining structured latent-space improvement with local action correction. Experiments show that, once CNDO narrows the gap between noise-space and action-space residual learning, CANDO further improves over single-space optimization, achieving 76.1 NAUC and a 91.4% final success rate, surpassing the best single-space results by 6.6 NAUC and 4.1% success rate. More demos and info are available on https://cando-rl.github.io/.

cs.LG↗

LAW: Unifying Language, Action, and World Modeling for Agentic Physical Intelligence

World-action models jointly predict actions and future world states, but long-horizon manipulation further requires language reasoning to plan subtask objectives, assess execution progress, and guide action selection. We present LAW, a closed-loop VLM--WAM framework that unifies language reasoning, action generation, and world modeling through semantic subtask progress. Within the LAW agent, a hybrid-expert vision-language model plans the remaining subtasks, estimates the values of and fuses actions proposed by a world-action model, and asynchronously assesses execution status to support continued execution and subtask transitions. Within the world-action model, Mixture-of-Transformer Experts integrates modality-specific and shared computation for joint video--action modeling. Dual-stream hierarchical visual memory maintains temporal context for both models, while subtask-local value learning aligns action evaluation with semantic objectives and preserves supervision from successful prefixes of failed trajectories. LAW achieves 94.21% average success across 50 RoboTwin tasks. Replacing the WAM backbone with OpenWAM-$alpha$ further raises the average success rate to 95.56%, establishing a new open-source state of the art on RoboTwin. Despite having only 2B parameters, our VLM also outperforms variants using Embodied-R1.5 and GPT-5.5 High. On three long-horizon real-robot tasks, LAW achieves 65% average success, compared with 28.33% for $pi_{0.5}$ and 25% for Fast-WAM.

cs.RO↗

Do Robotic World Models Really Follow Actions? Diagnosing and Aligning Action-Conditioned Generation for Policy Learning

Action-conditioned world models increasingly serve as learned simulators for robotic policy improvement, yet their reliability rests on an unverified assumption: generated futures faithfully reflect the consequences of arbitrary valid actions. Systematic evaluation against action-specific ground truth remains limited beyond expert demonstrations. To address this gap, we introduce WorldEcho, which evaluates action following over a broader action distribution through visual integrity and SE(3) end-effector trajectory alignment. Our diagnosis shows that expert-trained models perform better on demonstrated actions but struggle with off-expert trajectories, producing motion inconsistent with the commanded actions or visually invalid rollouts. To mitigate these failures, we propose WorldSync, which broadens action coverage, grounds intermediate video representations in action-induced robot dynamics through an Action-Forcing Expert, and aligns predicted and ground-truth changes under action interventions. Experiments show that WorldSync reduces integrity-gated error on RoboTwin and, when used for iterative policy improvement, yields higher success rates in simulation and on real robots.

cs.RO↗

HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation

Humans achieve complex manipulation through coordinated whole-body control, whereas most Vision-Language-Action (VLA) models treat robot body parts largely independently, making high-DoF humanoid control challenging and often unstable. We present HEX, a state-centric framework for coordinated manipulation on full-sized bipedal humanoid robots. HEX introduces a humanoid-aligned universal state representation for scalable learning across heterogeneous embodiments, and incorporates a Mixture-of-Experts Unified Proprioceptive Predictor to model whole-body coordination and temporal motion dynamics from large-scale multi-embodiment trajectory data. To efficiently capture temporal visual context, HEX uses lightweight history tokens to summarize past observations, avoiding repeated encoding of historical images during inference. It further employs a residual-gated fusion mechanism with a flow-matching action head to adaptively integrate visual-language cues with proprioceptive dynamics for action generation. Experiments on real-world humanoid manipulation tasks show that HEX achieves state-of-the-art performance in task success rate and generalization, particularly in fast-reaction and long-horizon scenarios.

cs.RO↗

SafeDojo: Safe Reinforcement Learning for VLA via Interactive World Model

Safe control is a prerequisite for real-world embodied intelligence, for which safe reinforcement learning has emerged as a promising paradigm. However, existing safe reinforcement learning methods either require costly real-world exploration or depend on hand-crafted safety functions. Neither scales to vision-language-action models deployed in open-world physical environments. We propose SafeDojo, a model-based safe reinforcement learning framework that improves vision-language-action policies through world-model imagination. SafeDojo performs online reinforcement learning on top of an interactive video world model. A ResNet success classifier scores predicted future frames, while a lightweight safety head predicts per-step contact probabilities from the current latent context and proposed action chunk, jointly assessing task execution and trajectory safety. These decoupled signals are balanced through Lagrangian-constrained GRPO. On SafeLIBERO Level I, SafeDojo improves average safe-success rate by 8.25 percentage points over the strongest baseline; on the zero-shot Level II setting, it is competitive with the strongest model-free baseline. Real-world Franka deployment further shows the best average task and safe-success rates across five tasks. These results support world-model-based safe reinforcement learning as a promising path toward safer embodied intelligence.

cs.RO↗

Physical Words: A Vocabulary for Structuring Latent Reasoning in Robot Manipulation

Multimodal reasoning provides robotic foundation models with predictive context needed for reliable action generation. However, language-based reasoning captures task semantics but struggles to express fine-grained physical dynamics, while latent reasoning models future state evolution but offers limited structure for organizing these dynamics into reusable reasoning primitives. To bridge this gap, we introduce PhysWord, a reasoning-before-acting foundation model built on Physical Words, which use atomic action verbs as shared semantic anchors for continuous representations of physical dynamics. Specifically, PhysWord predicts upcoming atomic action words and directly aligns their contextual hidden states with latent targets derived from the corresponding future observations. Building on these primitives, we construct a temporally structured PhysWord space with visual and optional tactile variants of each action word. Autoregressively predicting Physical Words across future timesteps captures transitions between execution stages, providing structured multimodal context for action generation. PhysWord achieves state-of-the-art success rates of 90.3\% on visuotactile UniVTAC and 99.6\% on vision-based LIBERO-Long, and outperforms competing methods on real-world tasks using bimanual grippers and dexterous hands. Further evaluations demonstrate that our structured latent reasoning framework generalizes to unseen scenarios and enables long-horizon manipulation. Project page: https://nvidia-isaac.github.io/video_to_data/physicalword/

cs.RO↗

Large Multimodal Models for Direct Robot Control: GPT-6 as a Beginning

Recent advances in visuospatial understanding and agentic reasoning enable direct robotic manipulation with general-purpose multimodal models, but their embodied capabilities remain poorly understood. This paper systematically evaluate GPT-6 Astra for closed-loop robotic manipulation using a lightweight agent execution framework. We first probe three fundamental embodied capabilities-depth perception, embodied in-context learning, and tactile understanding-and demonstrate that the model can exploit depth information, acquire simple manipulation strategies from contextual demonstrations, and use tactile feedback to correct its actions. We then evaluate GPT-6 Astra across five established manipulation benchmarks along six capability dimensions. Despite competitive performance on several benchmarks-26.92\% success on RoboDojo and 76.0\% on RoboTwin 2.0-our analysis reveals a pronounced gap between semantic reasoning and physical execution, particularly in consequence-aware action planning, precision, and complex motion coordination. To further examine these limitations, we introduce LIBERO-GeoMotion, a new benchmark of geometry-constrained tasks that require precise pose alignment, coordinated translation and rotation, and anticipation of physical action consequences. GPT-6 Astra achieves only 11.1\% zero-shot success, exposing the difficulty of translating spatial understanding into physically feasible motion. Real-world experiments corroborate these findings: zero-shot execution is feasible for simple tasks, yet persistent deficits remain in motion feasibility, precise control, and physical safety, while substantial inference latency further hinders practical deployment. Overall, our results characterize the emerging embodied capabilities of general-purpose multimodal models and delineate the key challenges toward safe, efficient, and reliable robotic manipulation.

cs.RO↗

HAF-VLA: Hierarchical Action Flow Framework for Humanoid Vision-Language-Action Control

Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet adapting generalist vision-language-action (VLA) policies to real-world humanoid loco-manipulation remains challenging. Unlike fixed-base or wheeled manipulators, humanoids must coordinate locomotion, posture, gaze, and dual-arm manipulation over a high-dimensional whole-body action space, where inaccurate base or waist motions can easily induce unstable and aggressive upper-body compensation. We propose HAF-VLA, a hierarchical action-flow framework for humanoid VLA control. Built upon a pretrained flow-matching VLA, HAF-VLA inherits the vision-language prefix encoder and action expert weights, and adapts them to humanoid whole-body loco-manipulation with learnable stage embeddings and cross-stage KV-cache conditioning. Instead of generating the full action chunk in a single pass, HAF-VLA progressively denoises a shared whole-body action space: first locomotion and head commands, then waist refinement, and finally full-body manipulation. To preserve structural dependencies across stages, we introduce a cross-stage KV cache conditioning mechanism, enabling subsequent action generation stages to refine and augment their outputs based on the action representations from preceding stages. Experimental results across six real-world tasks demonstrate that our framework significantly enhances the performance of existing models in humanoid loco-manipulation tasks, demonstrating an effective pathway for adapting strong mobile-manipulation VLAs to humanoid whole-body loco-manipulation.

cs.RO↗

TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference

Multimodal large language models (MLLMs) have achieved strong multimodal reasoning capabilities, but their efficiency is limited by the large number of visual tokens, which introduces substantial computational overhead. Visual token pruning offers a natural solution, yet existing methods are imperfect: attention-based criteria tend to retain redundant tokens, while diversity-based criteria are often agnostic to user instructions. Even methods that combine multiple criteria still lack a principled formulation of the intrinsic objective of token pruning. In this paper, we revisit visual token pruning from a first-principles perspective and formulate it as constructing Token Optimal Preservation Sets. Through a top-down information-theoretic analysis, we identify three fundamental principles for effective token selection: Task Relevance, Information Coverage, and Semantic Diversity. Based on these principles, we propose TOPS, a training-free and model-agnostic pruning module that can be applied to various MLLMs. Extensive experiments on 7 MLLM backbones and 14 benchmarks demonstrate that TOPS outperforms prior methods under diverse pruning settings. Notably, on LLaVA-NeXT, TOPS removes 77.8% of visual tokens while preserving 100.0% and 100.6% performance on its 7B and 13B models, respectively, suggesting that pruning redundant visual tokens can sometimes mitigate hallucination and inspire future lightweight MLLM design. Our code is available at https://github.com/MAX-7237/TOPS.

cs.AI↗

MiCo: Mutual Information Coverage Optimization through Semantic Erasure Modeling for Efficient MLLM Inference

Multimodal large language models (MLLMs) have demonstrated impressive performance in multimodal understanding, but processing large numbers of visual tokens results in high computational costs. While many methods have been proposed to reduce the number of visual tokens, most of them rely on heuristics and are prone to discarding substantial visual information during pruning, leading to degradation in model performance. In this work, by using a semantic erasure model, we derive a general mutual information coverage objective from task log-loss and propose MiCo, a training-free two-stage pruning method. MiCo first uses visual signals to select a representative candidate pool before visual tokens enter the language model, then performs task-aware subset selection within it. At each stage, suitable observable proxies instantiate the derived objective as a monotone submodular coverage function, which MiCo greedily optimizes under the token budget. MiCo is evaluated on diverse MLLMs ranging from 7B to 13B parameters across a broad range of image and video benchmarks spanning general visual reasoning, fine-grained OCR and grounding, hallucination detection, and long-video understanding. MiCo consistently achieves the best performance across nearly all evaluated models under all pruning ratios. On LLaVA-NEXT-13B, MiCo uses only 5.6% visual tokens, retains 97.5% of baseline performance, and achieves a 3.8-fold inference speedup. Our experiments demonstrate the effectiveness of MiCo and our mutual information coverage objective for visual token pruning. Our code is available at https://github.com/MAX-7237/MiCo.

cs.CV↗

METIS: Multi-Source Egocentric Training for Integrated Dexterous Vision-Language-Action Model

Building a generalist robot that can perceive, reason, and act across diverse tasks remains an open challenge, especially for dexterous manipulation. A major bottleneck lies in the scarcity of large-scale, action-annotated data for dexterous skills, as teleoperation is difficult and costly. Human data, with its vast scale and diverse manipulation behaviors, provides rich priors for learning robotic actions. While prior works have explored leveraging human demonstrations, they are often constrained by limited scenarios and a large visual gap between human and robots. To eliminate these limitations, we propose METIS, a vision-language-action (VLA) model for dexterous manipulation pretrained on multi-source egocentric datasets. We first construct EgoAtlas, which integrates large-scale human and robotic data from multiple sources, all unified under a consistent action space. We further extract motion-aware dynamics, a compact and discretized motion representation, which provides efficient and expressive supervision for VLA training. Built upon them, METIS integrates reasoning and acting into a unified framework, enabling effective deployment to downstream dexterous manipulation tasks. Our method demonstrates exceptional dexterous manipulation capabilities, achieving highest average success rate in six real-world tasks. Experimental results also highlight the superior generalization and robustness to out-of-distribution scenarios. These findings emphasize METIS as a promising step toward a generalist model for dexterous manipulation.

cs.RO↗

MMG-Vid: Maximizing Marginal Gains at Segment-level and Token-level for Efficient Video LLMs

Video Large Language Models (VLLMs) excel in video understanding, but their excessive visual tokens pose a significant computational challenge for real-world applications. Current methods aim to enhance inference efficiency by visual token pruning. However, they do not consider the dynamic characteristics and temporal dependencies of video frames, as they perceive video understanding as a multi-frame task. To address these challenges, we propose MMG-Vid, a novel training-free visual token pruning framework that removes redundancy by Maximizing Marginal Gains at both segment-level and token-level. Specifically, we first divide the video into segments based on frame similarity, and then dynamically allocate the token budget for each segment to maximize the marginal gain of each segment. Subsequently, we propose a temporal-guided DPC algorithm that jointly models inter-frame uniqueness and intra-frame diversity, thereby maximizing the marginal gain of each token. By combining both stages, MMG-Vid can maximize the utilization of the limited token budget, significantly improving efficiency while maintaining strong performance. Extensive experiments demonstrate that MMG-Vid can maintain over 99.5% of the original performance, while effectively reducing 75% visual tokens and accelerating the prefilling stage by 3.9x on LLaVA-OneVision-7B. Code is available at https://github.com/ylnxxts/MMG-Vid.

cs.CV↗

GIFT: Global Irreplaceability Frame Targeting for Efficient Video Understanding

Video Large Language Models (VLMs) have achieved remarkable success in video understanding, but the significant computational cost from processing dense frames severely limits their practical application. Existing methods alleviate this by selecting keyframes, but their greedy decision-making, combined with a decoupled evaluation of relevance and diversity, often falls into local optima and results in erroneously selecting irrelevant noise frames. To address these challenges, we propose GIFT: Global Irreplaceability Frame Targeting, a novel training-free framework that selects frames by assessing their intrinsic irreplaceability. Specifically, we first introduce Directed Diversity to quantify a frame's uniqueness conditioned on relevance, which allows us to formulate a unified irreplaceability score. Subsequently, our Budget-Aware Refinement strategy employs a adaptive iterative process that first secures a core set of frames with the highest irreplaceability, and then shifts its priority to building crucial temporal context around these selections as the budget expands. Extensive experiments demonstrate that GIFT achieves a maximum average improvement of 12.5% across long-form video benchmarks on LLaVA-Video-7B compared to uniform sampling. Code is available at https://github.com/ylnxxts/GIFT.

cs.CV↗

World-Ego Modeling for Embodied Video Generation in Long-Horizon Navigation-Manipulation Tasks

Embodied video world models typically capture both scene evolution and the robot's behavior, which we refer to as the \emph{world} and the \emph{ego}, respectively. The world and the ego exhibit different underlying dynamics: world prediction relies primarily on visual history and emphasizes scene stability, whereas ego prediction relies more strongly on the current instruction and emphasizes accurate instruction following. Modeling both components within a single generation stream can entangle these different dependencies, making it difficult to specialize the prediction of either component. Consequently, it becomes difficult to simultaneously maintain scene consistency and accurate instruction following, particularly in long-horizon navigation-manipulation tasks. In this paper, we propose to decompose an embodied video into the world and the ego and disentangle their generation processes. Specifically, we define the world as the background and currently unmanipulated objects, and the ego as the robot and currently manipulated objects. Based on this definition, we develop the \emph{World-Ego Model} (WEM), which combines a vision-language state predictor using role-conditioned attention (RCA) and asymmetric query budgets with a semantic-routed mixture-of-experts (SR-MoE) diffusion generator. To enable rigorous evaluation, we further construct HTEWorld, a dataset and benchmark for long-horizon embodied video generation with hybrid navigation-manipulation tasks, providing 125K training video clips comprising over 4.5M frames with fine-grained instructions, together with 300 multi-turn evaluation trajectories covering over 2K instructions. Extensive experiments show that WEM achieves state-of-the-art performance on HTEWorld while remaining competitive on existing manipulation-oriented evaluations.

cs.CV↗